Unlock instant, AI-driven research and patent intelligence for your innovation.

Brushless DC motor position sensing method based on support vector machine (SVM) decision classification

A technology of support vector machine and brush DC motor, which is applied in the control of electromechanical transmission, control of generator, motor generator control, etc., can solve problems such as difficult to use motor operation requirements, and achieve good dynamic performance, high robustness, The effect of improving the reaction speed

Inactive Publication Date: 2019-01-11
HUNAN UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Technical problem: The rotor signal detection methods with position sensor and various position sensorless devices have their limitations, so it is difficult to apply to occasions with relatively high requirements for motor operation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Brushless DC motor position sensing method based on support vector machine (SVM) decision classification
  • Brushless DC motor position sensing method based on support vector machine (SVM) decision classification
  • Brushless DC motor position sensing method based on support vector machine (SVM) decision classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The brushless DC motor position sensing method based on support vector machine one-to-many classification proposed by the present invention, combined with the system structure diagram, is described in detail as follows:

[0039] Step1: Input and output detection signals for the acquisition system of the same model brushless DC motor with position sensor: A and B phase voltage

[0040] u a (k),u b (k) Current i a (k),i b (k),i a (k-1),i b (k-1) as the input of the support vector machine, S(K) is the rotor position

[0041] Set signal, use it as the output of the support vector machine, and divide the 0-360 degree electrical angle of the rotor of the DC motor into each

[0042] There are 6 zones in one zone at 60 degrees, and the rotor position is indicated by the zone number 1-6.

[0043] Step2: A total of 15 support vector machine 2 classifiers are set up. The first level of 1 classifier will set the samples of non-category 1 (2-6 categories) as positive samples, and the samples ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a brushless DC motor position sensing method based on support vector machine (SVM) decision classification aiming at the problem of brushless DC motor rotor position detection.The position sensing control based on SVM multi-classification takes the stator voltage and current of the brushless DC motor as inputs of the decision SVM and the rotor position information as outputs, divides the rotor position of the DC motor into six regions, and the rotor position is determined by using the region serial number 1. The rotor position of the brushless DC motor is divided into six regions. 6, set 15 SVM binary classifiers for hierarchical classification decision. The optimal parameters of SVM are determined by training SVM network with mesh optimization method. Then the trained network model is applied to the motor operation, the stator voltage and current of the motor are collected as the input of SVM, the final rotor position information is determined by hierarchical decision-making, the commutation signal is calculated by rotor position estimation logic, and the on-off signal of the corresponding switch tube corresponding to each area is determined, that is, commutation logic signal.

Description

Technical field [0001] The invention relates to a rotor position sensing method in the field of brushless DC motors, in particular to a brushless DC motor position sensing method based on support vector machine (SVM) decision classification. Background technique [0002] The brushless DC motor uses the rotor position signal to control the electronic commutation circuit to continuously commutate each winding of the stator armature, so that the stator magnetic field and the rotor permanent magnetic field always maintain a space angle of about 90, generating torque to drive the rotor to run. [0003] The rotor position information of the traditional brushless DC motor is measured by a position sensor, and a position detection device needs to be installed, but the brushless DC motor with a position detection device has the following disadvantages: increase the size of the motor, which is not conducive to the miniaturization of the motor; the installation of the position sensor In the v...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): H02P21/18
CPCH02P21/18
Inventor 王欣秦羽新秦斌
Owner HUNAN UNIV OF TECH